Fully automatic framework for comprehensive coronary artery calcium scores analysis on non-contrast cardiac-gated CT scan: Total and vessel-specific quantifications

Automated AI-based coronary calcium scoring using retrospective CT data from SCAPIS is accurate and correlates with expert scoring

OBJECTIVES

Evaluation of the correlation and agreement between AI and semi-automatic evaluations of calcium scoring CT (CSCT) examinations using extensive data from the Swedish CardioPulmonary bio-Image study (SCAPIS).

MATERIALS AND METHODS

In total, 5057 CSCT examinations were performed on one CT system at Linköping University Hospital between October 8, 2015, and June 12, 2018. AI evaluations were compared to semi-automatic CSCT results from expert reader evaluations rendered within SCAPIS. Pearson correlation, intraclass correlation coefficients (ICC), and Bland-Altman analysis were applied for Agatston (AS), volume (VS), mass scores (MS), number of lesions and lesion location. Agreement of Agatston score classifications into cardiovascular (CV) risk categories was evaluated with weighted kappa analysis.

RESULTS

The evaluation included 4567 subjects, 2229 (48.8%) male, 2338 (51.2%) female, 50-64 years of age (mean 57.3 ± 4.4). The AS ranged from 0 to 2871 in the cohort, with 2846 subjects having an AS of 0. Mean and median AS were 51.4 and 0.0, respectively. Total AS, VS, MS and number of lesions ICCs were 0.994, 0.994, 0.994, 0.960 (p < 0.001), respectively. Bland-Altman analyses rendered mean differences ± 1.96 SD upper and lower limits of agreement for AS -0.04, -52.5 to 52.4, VS -0.44, -46.51 to 45.63, and MS -0.07, -9.62 to 9.48. Weighted kappa analysis for CV risk category classifications was 0.913, and overall accuracy was 91.2%.

CONCLUSION

There was excellent correlation and agreement between AI and semi-automatic evaluations for all calcium scores, number of lesions and lesion location. High degrees of agreement and accuracy were found for the CV risk categorization.

KEY POINTS

Question Can AI function as a tool for enhancing the efficiency and accuracy of Coronary Artery Calcium Score (CACS) evaluations in clinical radiology practice? Findings This study confirms the robustness of AI-derived CACS results across extensive datasets, though its generalizability is limited by data acquisition from a single CT system. Clinical relevance This study suggests that AI holds significant promise as a tool for enhancing the efficiency and accuracy of CACS evaluations, with implications for improving patient diagnostics and reducing radiologist workload in clinical practice.

Correlation Between Coronary Arterial Dominance and the Degree of Coronary Artery Disease Using Computed Tomography Angiography

Objective

This study used Computed Tomography Angiography to evaluate how coronary artery dominance affects CAD severity.

Methods

We retrospectively examined 1,000 coronary CTA patients at five private outpatient radiography clinics in Amman, Jordan. Patients of both sexes aged 18 or older with no coronary CTA contraindications were enrolled. Two 10-year-experienced radiologists reviewed all coronary CT images with 64 slices or more without knowing the patients' medical histories.

Results

The coronary arteries were right, left, or co-dominant. CAD: stenosis. Visual assessment of the lumen diameter rated coronary stenosis as 0%, mild (1-49%), moderate (50-69%), or severe (≥70%). Positive obstructive CAD can be identified when a coronary lesion compromises the lumen by ≥50%. A CAD patient had one, two, three, or four vascular disease. Study outcomes were assessed using descriptive statistics, t-tests, and one-way ANOVA. Right, left, and co-dominant coronary arteries predominated 85.7%, 11.6%, and 2.7%. Co-dominance caused greater right coronary artery (RCA) issues than left- or right-dominance. 22.2% of co-dominance patients reported positive RCA difficulties, compared to 6.9% and 21.0% of left- and right-dominance patients (p = 0.001). In addition, 14.8% of co-dominance patients had obstructive RCA lesions, compared to 1.7% of left-dominance and 5.3% of right-dominance (p = 0.018). The coronary dominance patterns did not affect LMCA, LAD, LCX, and Ramus blockages (p = 0.846, 0.447, 0.116, and 0.867). Calcium scores averaged 44.4 for right dominance, 41.0 for left, and 86.2 for co-dominance (p = 0.136).

Conclusion

Coronary CTA may not provide more risk information than assessing stenosis in patients with normal arteries or non-significant CAD. However, it may aid RCA and obstructive CAD patients.

Fully automated coronary artery calcium score and risk categorization from chest CT using deep learning and multiorgan segmentation: A validation study from National Lung Screening Trial (NLST)

Background

The National Lung Screening Trial (NLST) has shown that screening with low dose CT in high-risk population was associated with reduction in lung cancer mortality. These patients are also at high risk of coronary artery disease, and we used deep learning model to automatically detect, quantify and perform risk categorisation of coronary artery calcification score (CACS) from non-ECG gated Chest CT scans.

Materials and methods

Automated calcium quantification was performed using a neural network based on Mask regions with convolutional neural networks (R-CNN) for multiorgan segmentation. Manual evaluation of calcium was carried out using proprietary software. This study used 80 patients to train the segmentation model and randomly selected 1442 patients were used for the validation of the algorithm. We compared the model generated results with Ground Truth.

Results

Automatic cardiac and aortic segmentation model worked well (Mean Dice score: 0.91). Cohen's kappa coefficient between the reference actual and the interclass computed predictive categories on the test set is 0.72 (95 % CI: 0.61-0.83). Our method correctly classifies the risk group in 78.8 % of the cases and classifies the subjects in the same group. F-score is measured as 0.78; 0.71; 0.81; 0.82; 0.92 in calcium score categories 0(CS:0), I (1-99), II (100-400), III (400-1000), IV (>1000), respectively. 79 % of the predictive scores lie in the same categories, 20 % of the predictive scores are one category up or down, and only 1.2 % patients were more than one category off. For the presence/absence of coronary artery calcifications, our deep learning model achieved a sensitivity of 90 % and a specificity of 94 %.

Conclusion

Fully automated model shows good correlation compared with reference standards. Automating the process could improve diagnostic ability, risk categorization, facilitate primary prevention intervention, improve morbidity and mortality, and decrease healthcare costs.

Artificial intelligence-derived coronary artery calcium scoring saves time and achieves close to radiologist-level accuracy accuracy on routine ECG-gated CT

Artificial Intelligence (AI) has been proposed to improve workflow for coronary artery calcium scoring (CACS), but simultaneous demonstration of improved efficiency, accuracy, and clinical stability have not been demonstrated. 148 sequential patients who underwent routine calcium-scoring computed tomography were retrospectively evaluated using a previously validated AI model (syngo. CT CaScoring VB60, Siemens Healthineers, Forscheim, Germany). CACS was performed by manual (Expert alone), semi-automatic (AI + expert review), and automatic (AI alone) methods. Time to complete and intraclass correlation coefficients were the primary endpoints. Secondary endpoints included differences in multiethnic study of atherosclerosis (MESA) percentiles and stratification by calcium severity. AI and expert CACS agreement was excellent (ICC = 0.951; 95% CI 0.933-0.964). The global median time was 15 ± 2 s for AI ("Automatic"), 38 ± 13 s for the AI + manual review ("Semiautomatic") and 45 ± 24 s for the manual segmentation. Automatic segmentation was faster than manual segmentation for all CACS severities (P < 0.001). AI computational time was independent of calcium burden. Global mean bias in Agatston score across all patients was 7.4 ± 102.6. The mean bias for global MESA score percentile was 2.1% ± 12%. 95% of error corresponded to a ± 10% difference in MESA score. The use of AI for CACS performs excellent accuracy, saves approximately 60% of time in comparison to manual review, and demonstrates low bias for clinical risk profiles. Time benefits are magnified for patients with high CACS. However, a semi-automatic approach is still recommended to minimize potential errors while maintaining efficiency.

Artificial Intelligence in Ischemic Heart Disease Prevention

PURPOSE OF REVIEW

This review discusses the transformative potential of artificial intelligence (AI) in ischemic heart disease (IHD) prevention. It explores advancements of AI in predictive modeling, biomarker discovery, and cardiovascular imaging. Finally, considerations for clinical integration of AI into preventive cardiology workflows are reviewed.

RECENT FINDINGS

AI-driven tools, including machine learning (ML) models, have greatly enhanced IHD risk prediction by integrating multimodal data from clinical sources, patient-generated inputs, biomarkers, and imaging. Applications in these various data sources have demonstrated superior diagnostic accuracy compared to traditional methods. However, ensuring algorithm fairness, mitigating biases, enhancing explainability, and addressing ethical concerns remain critical for successful deployment. Emerging technologies like federated learning and explainable AI are fostering more robust, scalable, and equitable adoption. AI holds promise in reshaping preventive cardiology workflows, offering more precise risk assessment and personalized care. Addressing barriers related to equity, transparency, and stakeholder engagement is key for seamless clinical integration and sustainable, lasting improvements in cardiovascular care.

Performance of artificial intelligence in detecting the chronic total occlusive lesions of coronary artery based on coronary computed tomographic angiography

Background

Coronary chronic total occlusion (CTO) increases the risk of developing major adverse cardiovascular events (MACE) and cardiogenic shock. Coronary computed tomography angiography (CCTA) is a safe, noninvasive method to diagnose CTO lesions. With the development of artificial intelligence (AI), AI has been broadly applied in cardiovascular images, but AI-based detection of CTO lesions from CCTA images is difficult. We aim to evaluate the performance of AI in detecting the CTO lesions of coronary arteries based on CCTA images.

Methods

We retrospectively and consecutively enrolled patients with 50% stenosis, 50-99% stenosis, and CTO lesions who received CCTA scans between June 2021 and June 2022 in Beijing Anzhen Hospital. Four-fifths of them were randomly assigned to the training dataset, while the rest (1/5) were randomly assigned to the testing dataset. Performance of the AI-assisted CCTA (CCTA-AI) in detecting the CTO lesions was evaluated through sensitivity, specificity, positive predictive value, negative predictive value, accuracy, and receiver operating characteristic analysis. With invasive coronary angiography as the reference, the diagnostic performance of AI method and manual method was compared.

Results

A total of 537 patients with 1,569 stenotic lesions (including 672 lesions with <50% stenosis, 493 lesions with 50-99% stenosis, and 404 CTO lesions) were enrolled in our study. CCTA-AI saved 75% of the time in post-processing and interpreting the CCTA images when compared to the manual method (116±15 vs. 472±45 seconds). In the testing dataset, the accuracy of CCTA-AI in detecting CTO lesions was 86.2% (79.0%, 90.3%), with the area under the curve of 0.874. No significant difference was found in detecting CTO lesions between AI and manual methods (P=0.53).

Conclusions

AI can automatically detect CTO lesions based on CCTA images, with high diagnostic accuracy and efficiency.

Artificial Intelligence in Cardiovascular Disease Prevention: Is it Ready for Prime Time?

PURPOSE OF REVIEW

This review evaluates how Artificial Intelligence (AI) enhances atherosclerotic cardiovascular disease (ASCVD) risk assessment, allows for opportunistic screening, and improves adherence to guidelines through the analysis of unstructured clinical data and patient-generated data. Additionally, it discusses strategies for integrating AI into clinical practice in preventive cardiology.

RECENT FINDINGS

AI models have shown superior performance in personalized ASCVD risk evaluations compared to traditional risk scores. These models now support automated detection of ASCVD risk markers, including coronary artery calcium (CAC), across various imaging modalities such as dedicated ECG-gated CT scans, chest X-rays, mammograms, coronary angiography, and non-gated chest CT scans. Moreover, large language model (LLM) pipelines are effective in identifying and addressing gaps and disparities in ASCVD preventive care, and can also enhance patient education. AI applications are proving invaluable in preventing and managing ASCVD and are primed for clinical use, provided they are implemented within well-regulated, iterative clinical pathways.

Artificial intelligence in coronary artery calcium score: rationale, different approaches, and outcomes

Almost 35 years after its introduction, coronary artery calcium score (CACS) not only survived technological advances but became one of the cornerstones of contemporary cardiovascular imaging. Its simplicity and quantitative nature established it as one of the most robust approaches for atherosclerotic cardiovascular disease risk stratification in primary prevention and a powerful tool to guide therapeutic choices. Groundbreaking advances in computational models and computer power translated into a surge of artificial intelligence (AI)-based approaches directly or indirectly linked to CACS analysis. This review aims to provide essential knowledge on the AI-based techniques currently applied to CACS, setting the stage for a holistic analysis of the use of these techniques in coronary artery calcium imaging. While the focus of the review will be detailing the evidence, strengths, and limitations of end-to-end CACS algorithms in electrocardiography-gated and non-gated scans, the current role of deep-learning image reconstructions, segmentation techniques, and combined applications such as simultaneous coronary artery calcium and pulmonary nodule segmentation, will also be discussed.

The Role of Artificial Intelligence in Coronary Calcium Scoring in Standard Cardiac Computed Tomography and Chest Computed Tomography With Different Reconstruction Kernels

PURPOSE

To assess the correlation of coronary calcium score (CS) obtained by artificial intelligence (AI) with those obtained by electrocardiography gated standard cardiac computed tomography (CCT) and nongated chest computed tomography (ChCT) with different reconstruction kernels.

PATIENTS AND METHODS

Seventy-six patients received standard CCT and ChCT simultaneously. We compared CS obtained in 4 groups: CS CCT , by the traditional method from standard CCT, 25 cm field of view, 3 mm slice thickness, and kernel filter convolution 12 (FC12); CS AICCT , by AI from the standard CCT; CS ChCTsoft , by AI from the non-gated CCT, 40 cm field of view, 3 mm slice thickness, and a soft kernel FC02; and CS ChCTsharp , by AI from CCT image with same parameters for CS ChCTsoft except for using a sharp kernel FC56. Statistical analyses included Spearman rank correlation coefficient (ρ), intraclass correlation (ICC), Bland-Altman plots, and weighted kappa analysis (κ).

RESULTS

The CS AICCT was consistent with CS CCT (ρ = 0.994 and ICC of 1.00, P < 0.001) with excellent agreement with respect to cardiovascular (CV) risk categories of the Agatston score (κ = 1.000). The correlation between CS ChCTsoft and CS ChCTsharp was good (ρ = 0.912, 0.963 and ICC = 0.929, 0.948, respectively, P < 0.001) with a tendency of underestimation (Bland-Altman mean difference and 95% upper and lower limits of agreements were 329.1 [-798.9 to 1457] and 335.3 [-651.9 to 1322], respectively). The CV risk category agreement between CS ChCTsoft and CS ChCTsharp was moderate (κ = 0.556 and 0.537, respectively).

CONCLUSIONS

There was an excellent correlation between CS CCT and CS AICCT , with excellent agreement between CV risk categories. There was also a good correlation between CS CCT and CS obtained by ChCT albeit with a tendency for underestimation and moderate accuracy in terms of CV risk assessment.

Artificial Intelligence in Coronary Artery Calcium Scoring Detection and Quantification

Coronary artery calcium (CAC) is a marker of coronary atherosclerosis, and the presence and severity of CAC have been shown to be powerful predictors of future cardiovascular events. Due to its value in risk discrimination and reclassification beyond traditional risk factors, CAC has been supported by recent guidelines, particularly for the purposes of informing shared decision-making regarding the use of preventive therapies. In addition to dedicated ECG-gated CAC scans, the presence and severity of CAC can also be accurately estimated on non-contrast chest computed tomography scans performed for other clinical indications. However, the presence of such "incidental" CAC is rarely reported. Advances in artificial intelligence have now enabled automatic CAC scoring for both cardiac and non-cardiac CT scans. Various AI approaches, from rule-based models to machine learning algorithms and deep learning, have been applied to automate CAC scoring. Convolutional neural networks, a deep learning technique, have had the most successful approach, with high agreement with manual scoring demonstrated in multiple studies. Such automated CAC measurements may enable wider and more accurate detection of CAC from non-gated CT studies, thus improving the efficiency of healthcare systems to identify and treat previously undiagnosed coronary artery disease.

Fully automated coronary artery calcium quantification on electrocardiogram-gated non-contrast cardiac computed tomography using deep-learning with novel Heart-labelling method

Aims

To develop an artificial intelligence (AI)-model which enables fully automated accurate quantification of coronary artery calcium (CAC), using deep learning (DL) on electrocardiogram (ECG)-gated non-contrast cardiac computed tomography (gated CCT) images.

Methods and results

Retrospectively, 560 gated CCT images (including 60 synthetic images) performed at our institution were used to train AI-model, which can automatically divide heart region into five areas belonging to left main (LM), left anterior descending (LAD), circumflex (LCX), right coronary artery (RCA), and another. Total and vessel-specific CAC score (CACS) in each scan were manually evaluated. AI-model was trained with novel Heart-labelling method via DL according to the manual-derived results. Then, another 409 gated CCT images obtained in our institution were used for model validation. The performance of present AI-model was tested using another external cohort of 400 gated CCT images of Stanford Center for Artificial Intelligence of Medical Imaging by comparing with the ground truth. The overall accuracy of the AI-model for total CACS classification was excellent with Cohen's kappa of k = 0.89 and 0.95 (validation and test, respectively), which surpasses previous research of k = 0.89. Bland-Altman analysis showed little difference in individual total and vessel-specific CACS between AI-derived CACS and ground truth in test cohort (mean difference [95% confidence interval] were 1.5 [-42.6, 45.6], -1.5 [-100.5, 97.5], 6.6 [-60.2, 73.5], 0.96 [-59.2, 61.1], and 7.6 [-134.1, 149.2] for LM, LAD, LCX, RCA, and total CACS, respectively).

Conclusion

Present Heart-labelling method provides a further improvement in fully automated, total, and vessel-specific CAC quantification on gated CCT.

The Value of Coronary Computed Tomography Angiography in Patients with a High Calcium Score

Background

We aimed to assess the agreement between coronary computed tomography angiography (CCTA) and invasive coronary angiography (ICA) to determine whether patients with a high coronary artery calcium score (CS) would benefit from CCTA.

Methods

This cross-sectional study was conducted on patients suspected of having coronary artery disease. The patients underwent calcium scoring. The total CS and the number of calcified foci were determined. The calcium score index (CSI) was defined, and coronary arteries were evaluated by CCTA. ICA was performed, and reports of ICA were extracted. All the abovementioned variables were compared. For data analysis, the κ coefficient and the ROC curve were used.

Results

The study population consisted of 195 patients: 124 men (63.6%) and 71 women (36.4%). The median (IQR) value of CS was 529 (229-1042), ranging from 17 to 4717. In all 195 patients, the concordance between the final impression of CCTA and ICA was 90.2%, while the number and type of involved territories were similar at 57.9%. The highest agreement was seen in the left main and right coronary arteries, whereas the lowest agreement was detected in the left anterior descending and the left circumflex artery. The patients were categorized into different CS groups, and in those with a high CS (>1000), the agreement between CCTA and ICA concerning final impression and involved territories was similar to the whole group of patients.

Conclusion

CCTA in patients with a high CS, even exceeding 1000, remains beneficial as the noninvasive available method.

Role and progress of artificial intelligence in radiodiagnosing vascular calcification: a narrative review

Background and Objective

Vascular calcification has important clinical significance due to its vital prognostic value for cardiovascular diseases, chronic kidney disease (CKD), diabetes, fracture, and other multisystem diseases. Radiology is the main diagnostic method of it, but facing great pressure such as the increasing workload and decreasing working accuracy rate. Therefore, radiology needs to find a way out to better realize the clinical value of vascular calcification. Artificial intelligence (AI) encompasses any algorithm imitating human intelligence. AI has shown great potential in image analysis, such as its high speed and accuracy, becoming the savior of the current situation. In order to promote more rational utilization, the role and progress of AI in this field were reviewed.

Methods

A search was conducted in PubMed and Web of Science. The key words included "artificial intelligence", "machine learning", "deep learning", and "vascular calcification". The qualitative analysis of literature was achieved through repeated deliberation after refining valuable content. The theme is the role and progress of AI in the diagnostic radiology of vascular calcification.

Key Content and Findings

Sixty-two articles were included. AI has been applied to the diagnostic radiology of 5 types of vascular calcification, including coronary artery calcification (CAC), thoracic aortic calcification (TAC), abdominal aortic calcification (AAC), carotid artery calcification, and breast artery calcification (BAC). Deep learning (DL), the latest technology in this field has been well applied and satisfactorily performed. Radiologists have been able to achieve efficient diagnosis of 5 types of vascular calcification through AI, with reliable accuracy.

Conclusions

Increasingly, advanced AI has achieved an accuracy comparable to that of human experts, with a faster speed. Moreover, the ability to reduce noise and artifacts enables more imaging equipment to obtain reliable quantification. AI has acquired the ability to cooperate with radiology departments in future work. However, the research in AAC and carotid artery calcification can be more in-depth, and more types of vascular calcification and more fields of radiology should be expanded to. The interpretation of results made by AI and the promotion of existing achievements to the development of other disciplines are also the focus in future.

Artificial intelligence-based full aortic CT angiography imaging with ultra-low-dose contrast medium: a preliminary study

OBJECTIVES

To further reduce the contrast medium (CM) dose of full aortic CT angiography (ACTA) imaging using the augmented cycle-consistent adversarial framework (Au-CycleGAN) algorithm.

METHODS

We prospectively enrolled 150 consecutive patients with suspected aortic disease. All received ACTA scans of ultra-low-dose CM (ULDCM) protocol and low-dose CM (LDCM) protocol. These data were randomly assigned to the training datasets (n = 100) and the validation datasets (n = 50). The ULDCM images were reconstructed by the Au-CycleGAN algorithm. Then, the AI-based ULDCM images were compared with LDCM images in terms of image quality and diagnostic accuracy.

RESULTS

The mean image quality score of each location in the AI-based ULDCM group was higher than that in the ULDCM group but a little lower than that in the LDCM group (all p < 0.05). All AI-based ULDCM images met the diagnostic requirements (score ≥ 3). Except for the image noise, the AI-based ULDCM images had higher attenuation value than the ULDCM and LDCM images as well as higher SNR and CNR in all locations of the aorta analyzed (all p < 0.05). Similar results were also seen in obese patients (BMI > 25, all p < 0.05). Using the findings of LDCM images as the reference, the AI-based ULDCM images showed good diagnostic parameters and no significant differences in any of the analyzed aortic disease diagnoses (all K-values > 0.80, p < 0.05).

CONCLUSIONS

The required dose of CM for full ACTA imaging can be reduced to one-third of the CM dose of the LDCM protocol while maintaining image quality and diagnostic accuracy using the Au-CycleGAN algorithm.

KEY POINTS

• The required dose of contrast medium (CM) for full ACTA imaging can be reduced to one-third of the CM dose of the low-dose contrast medium (LDCM) protocol using the Au-CycleGAN algorithm. • Except for the image noise, the AI-based ultra-low-dose contrast medium (ULDCM) images had better quantitative image quality parameters than the ULDCM and LDCM images. • No significant diagnostic differences were noted between the AI-based ULDCM and LDCM images regarding all the analyzed aortic disease diagnoses.

Validation of deep learning-based fully automated coronary artery calcium scoring using non-ECG-gated chest CT in patients with cancer

This study aimed to demonstrate clinical feasibility of deep learning (DL)-based fully automated coronary artery calcium (CAC) scoring software using non-electrocardiogram (ECG)-gated chest computed tomography (CT) from patients with cancer. Overall, 913 patients with colorectal or gastric cancer who underwent non-contrast-enhanced chest CT between 2013 and 2015 were included. Agatston scores obtained by manual segmentation of CAC on chest CT were used as reference. Reliability of automated CAC score acquisition was evaluated using intraclass correlation coefficients (ICCs). The agreement for cardiovascular disease (CVD) risk stratification was assessed with linearly weighted k statistics. ICCs between the manual and automated CAC scores were 0.992 (95% CI, 0.991 and 0.993, p<0.001) for total Agatston scores, 0.863 (95% CI, 0.844 and 0.880, p<0.001) for the left main, 0.964 (95% CI, 0.959 and 0.968, p<0.001) for the left anterior descending, 0.962 (95% CI, 0.956 and 0.966, p<0.001) for the left circumflex, and 0.980 (95% CI, 0.978 and 0.983, p<0.001) for the right coronary arteries. The agreement for cardiovascular risk was excellent (k=0.946, p<0.001). Current DL-based automated CAC software showed excellent reliability for Agatston score and CVD risk stratification using non-ECG gated CT scans and might allow the identification of high-risk cancer patients for CVD.

A Review of Artificial Intelligence in Cerebrovascular Disease Imaging: Applications and Challenges

BACKGROUND

A variety of emerging medical imaging technologies based on artificial intelligence have been widely applied in many diseases, but they are still limitedly used in the cerebrovascular field even though the diseases can lead to catastrophic consequences.

OBJECTIVE

This work aims to discuss the current challenges and future directions of artificial intelligence technology in cerebrovascular diseases through reviewing the existing literature related to applications in terms of computer-aided detection, prediction and treatment of cerebrovascular diseases.

METHODS

Based on artificial intelligence applications in four representative cerebrovascular diseases including intracranial aneurysm, arteriovenous malformation, arteriosclerosis and moyamoya disease, this paper systematically reviews studies published between 2006 and 2021 in five databases: National Center for Biotechnology Information, Elsevier Science Direct, IEEE Xplore Digital Library, Web of Science and Springer Link. And three refinement steps were further conducted after identifying relevant literature from these databases.

RESULTS

For the popular research topic, most of the included publications involved computer-aided detection and prediction of aneurysms, while studies about arteriovenous malformation, arteriosclerosis and moyamoya disease showed an upward trend in recent years. Both conventional machine learning and deep learning algorithms were utilized in these publications, but machine learning techniques accounted for a larger proportion.

CONCLUSION

Algorithms related to artificial intelligence, especially deep learning, are promising tools for medical imaging analysis and will enhance the performance of computer-aided detection, prediction and treatment of cerebrovascular diseases.

Automatic COVID-19 Lung Infection Segmentation through Modified Unet Model

The coronavirus (COVID-19) pandemic has had a terrible impact on human lives globally, with far-reaching consequences for the health and well-being of many people around the world. Statistically, 305.9 million people worldwide tested positive for COVID-19, and 5.48 million people died due to COVID-19 up to 10 January 2022. CT scans can be used as an alternative to time-consuming RT-PCR testing for COVID-19. This research work proposes a segmentation approach to identifying ground glass opacity or ROI in CT images developed by coronavirus, with a modified structure of the Unet model having been used to classify the region of interest at the pixel level. The problem with segmentation is that the GGO often appears indistinguishable from a healthy lung in the initial stages of COVID-19, and so, to cope with this, the increased set of weights in contracting and expanding the Unet path and an improved convolutional module is added in order to establish the connection between the encoder and decoder pipeline. This has a major capacity to segment the GGO in the case of COVID-19, with the proposed model being referred to as "convUnet." The experiment was performed on the Medseg1 dataset, and the addition of a set of weights at each layer of the model and modification in the connected module in Unet led to an improvement in overall segmentation results. The quantitative results obtained using accuracy, recall, precision, dice-coefficient, F1score, and IOU were 93.29%, 93.01%, 93.67%, 92.46%, 93.34%, 86.96%, respectively, which is better than that obtained using Unet and other state-of-the-art models. Therefore, this segmentation approach proved to be more accurate, fast, and reliable in helping doctors to diagnose COVID-19 quickly and efficiently.

Automated coronary artery calcium scoring using nested U-Net and focal loss

Coronary artery calcium (CAC) is a great risk predictor of the atherosclerotic cardiovascular disease and CAC scores can be used to stratify the risk of heart disease. Current clinical analysis of CAC is performed using onsite semiautomated software. This semiautomated CAC analysis requires experienced radiologists and radiologic technologists and is both demanding and time-consuming. The purpose of this study is to develop a fully automated CAC detection model that can quantify CAC scores. A total of 1,811 cases of cardiac examinations involving contrast-free multidetector computed tomography were retrospectively collected. We divided the database into the Training Data Set, Validation Data Set, Testing Data Set 1, and Testing Data Set 2. The Training, Validation, and Testing Data Set 1 contained cases with clinically detected CAC; Testing Data Set 2 contained those without detected calcium. The intraclass correlation coefficients between the overall standard and model-predicted scores were 1.00 for both the Training Data Set and Testing Data Set 1. In Testing Data Set 2, the model was able to detect clinically undetected cases of mild calcium. The results suggested that the proposed model’s automated detection of CAC was highly consistent with clinical semiautomated CAC analysis. The proposed model demonstrated potential for clinical applications that can improve the quality of CAC risk stratification.

Effect of Calcification Based on Computer-Aided System on CT-Fractional Flow Reserve in Diagnosis of Coronary Artery Lesion

This study was to analyze the diagnostic value of coronary computed tomography angiography (CCTA) and fractional flow reserve (FFR) based on computer-aided diagnosis (CAD) system for coronary lesions and the possible impact of calcification. 80 patients who underwent CCTA and FFR examination in hospital were selected as the subjects. The FFR value of 0.8 was used as the dividing line and divided into the ischemic group (FFR ≤ 0.8) and nonischemic group (FFR > 0.8). The basic data and imaging characteristics of patients were analyzed. The maximum diameter stenosis rate (MDS %), maximum area stenosis rate (MAS %), and napkin ring sign (NRS) in the ischemic group were significantly lower than those in the nonischemic group (P < 0.05). Remodeling index (RI) and eccentric index (EI) compared with the nonischemic group had no significant difference (P > 0.05). The total plaque volume (TPV), total plaque burden (TPB), calcified plaque volume (CPV), lipid plaque volume (LPV), and lipid plaque burden (LPB) in the ischemic group were significantly different from those in the non-ischemic group (P < 0.05). MAS % had the largest area under curve (AUC) for the diagnosis of coronary myocardial ischemia (0.74), followed by MDS % (0.69) and LPV (0.68). CT-FFR had high diagnostic sensitivity, specificity, accuracy, truncation value, and AUC area data for patients in the ischemic group and nonischemic group. The diagnostic sensitivity, specificity, accuracy, cutoff value, and AUC area data of CT-FFR were higher in the ischemic group (89.93%, 92.07%, 95.84%, 60.51%, 0.932) and nonischemic group (93.75%, 90.88%, 96.24%, 58.22%, 0.944), but there were no significant differences between the two groups (P > 0.05). In summary, CT-FFR based on CAD system has high accuracy in evaluating myocardial ischemia caused by coronary artery stenosis, and within a certain range of calcification scores, calcification does not affect the diagnostic accuracy of CT-FFR.

Calcium Scoring at Coronary CT Angiography Using Deep Learning

Background Separate noncontrast CT to quantify the coronary artery calcium (CAC) score often precedes coronary CT angiography (CTA). Quantifying CAC scores directly at CTA would eliminate the additional radiation produced at CT but remains challenging. Purpose To quantify CAC scores automatically from a single CTA scan. Materials and Methods In this retrospective study, a deep learning method to quantify CAC scores automatically from a single CTA scan was developed on training and validation sets of 292 patients and 73 patients collected from March 2019 to July 2020. Virtual noncontrast scans obtained with a spectral CT scanner were used to develop the algorithm to alleviate tedious manual annotation of calcium regions. The proposed method was validated on an independent test set of 240 CTA scans collected from three different CT scanners from August 2020 to November 2020 using the Pearson correlation coefficient, the coefficient of determination, or r², and the Bland-Altman plot against the semiautomatic Agatston score at noncontrast CT. The cardiovascular risk categorization performance was evaluated using weighted κ based on the Agatston score (CAC score risk categories: 0-10, 11-100, 101-400, and >400). Results Two hundred forty patients (mean age, 60 years ± 11 [standard deviation]; 146 men) were evaluated. The positive correlation between the automatic deep learning CTA and semiautomatic noncontrast CT CAC score was excellent (Pearson correlation = 0.96; r² = 0.92). The risk categorization agreement based on deep learning CTA and noncontrast CT CAC scores was excellent (weighted κ = 0.94 [95% CI: 0.91, 0.97]), with 223 of 240 scans (93%) categorized correctly. All patients who were miscategorized were in the direct neighboring risk groups. The proposed method's differences from the noncontrast CT CAC score were not statistically significant with regard to scanner (P = .15), sex (P = .051), and section thickness (P = .67). Conclusion A deep learning automatic calcium scoring method accurately quantified coronary artery calcium from CT angiography images and categorized risk. © RSNA, 2021 See also the editorial by Goldfarb and Cao et al in this issue.

Fully Automatic Coronary Calcium Score Software Empowered by Artificial Intelligence Technology: Validation Study Using Three CT Cohorts

Objective

This study aimed to validate a deep learning-based fully automatic calcium scoring (coronary artery calcium [CAC]_auto) system using previously published cardiac computed tomography (CT) cohort data with the manually segmented coronary calcium scoring (CAC_hand) system as the reference standard.

Materials and Methods

We developed the CAC_auto system using 100 co-registered, non-enhanced and contrast-enhanced CT scans. For the validation of the CAC_auto system, three previously published CT cohorts (n = 2985) were chosen to represent different clinical scenarios (i.e., 2647 asymptomatic, 220 symptomatic, 118 valve disease) and four CT models. The performance of the CAC_auto system in detecting coronary calcium was determined. The reliability of the system in measuring the Agatston score as compared with CAC_hand was also evaluated per vessel and per patient using intraclass correlation coefficients (ICCs) and Bland-Altman analysis. The agreement between CAC_auto and CAC_hand based on the cardiovascular risk stratification categories (Agatston score: 0, 1–10, 11–100, 101–400, > 400) was evaluated.

Results

In 2985 patients, 6218 coronary calcium lesions were identified using CAC_hand. The per-lesion sensitivity and false-positive rate of the CAC_auto system in detecting coronary calcium were 93.3% (5800 of 6218) and 0.11 false-positive lesions per patient, respectively. The CAC_auto system, in measuring the Agatston score, yielded ICCs of 0.99 for all the vessels (left main 0.91, left anterior descending 0.99, left circumflex 0.96, right coronary 0.99). The limits of agreement between CAC_auto and CAC_hand were 1.6 ± 52.2. The linearly weighted kappa value for the Agatston score categorization was 0.94. The main causes of false-positive results were image noise (29.1%, 97/333 lesions), aortic wall calcification (25.5%, 85/333 lesions), and pericardial calcification (24.3%, 81/333 lesions).

Conclusion

The atlas-based CAC_auto empowered by deep learning provided accurate calcium score measurement as compared with manual method and risk category classification, which could potentially streamline CAC imaging workflows.